Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks

Abstract

Heterogeneous information networks (HINs) are ubiquitous in real-world applications. In the meantime, network embedding has emerged as a convenient tool to mine and learn from networked data. As a result, it is of interest to develop HIN embedding methods. However, the heterogeneity in HINs introduces not only rich information but also potentially incompatible semantics, which poses special challenges to embedding learning in HINs. With the intention to preserve the rich yet potentially incompatible information in HIN embedding, we propose to study the problem of comprehensive transcription of heterogeneous information networks. The comprehensive transcription of HINs also provides an easy-to-use approach to unleash the power of HINs, since it requires no additional supervision, expertise, or feature engineering. To cope with the challenges in the comprehensive transcription of HINs, we propose the HEER algorithm, which embeds HINs via edge representations that are further coupled with properly-learned heterogeneous metrics. To corroborate the efficacy of HEER, we conducted experiments on two large-scale real-words datasets with an edge reconstruction task and multiple case studies. Experiment results demonstrate the effectiveness of the proposed HEER model and the utility of edge representations and heterogeneous metrics. The code and data are available at https://github.com/GentleZhu/HEER.

arXiv comment10 pages. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, United Kingdom, ACM, 2018

References in corpus (9)

• Distributed Representations of Words and Phrases and their Compositionality
• DeepWalk: Online Learning of Social Representations
• LINE: Large-scale Information Network Embedding
• struc2vec: Learning Node Representations from Structural Identity
• PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks
• Discriminative Embeddings of Latent Variable Models for Structured Data
• Poincaré Embeddings for Learning Hierarchical Representations
• Learning Edge Representations via Low-Rank Asymmetric Projections
• PReP: Path-Based Relevance from a Probabilistic Perspective in Heterogeneous Information Networks

Cited by in corpus (26)

• Interpretable and Efficient Heterogeneous Graph Convolutional Network
• IntentGC: a Scalable Graph Convolution Framework Fusing Heterogeneous Information for Recommendation
• Is a Single Vector Enough? Exploring Node Polysemy for Network Embedding
• Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
• Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization
• PANE: scalable and effective attributed network embedding
• BHIN2vec: Balancing the Type of Relation in Heterogeneous Information Network
• Unsupervised Differentiable Multi-aspect Network Embedding
• HeteSpaceyWalk: A Heterogeneous Spacey Random Walk for Heterogeneous Information Network Embedding
• Heterogeneous Graph Attention Network
• A Heterogeneous Dynamical Graph Neural Networks Approach to Quantify Scientific Impact
• ActiveHNE: Active Heterogeneous Network Embedding
• Beyond Node Embedding: A Direct Unsupervised Edge Representation Framework for Homogeneous Networks
• Tree Structure-Aware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning
• JSCN: Joint Spectral Convolutional Network for Cross Domain Recommendation
• Heterogeneous network approach to predict individuals' mental health
• Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity
• Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learning
• Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks
• Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path
• Detect Camouflaged Spam Content via StoneSkipping: Graph and Text Joint Embedding for Chinese Character Variation Representation
• Task-Guided Pair Embedding in Heterogeneous Network
• mSHINE: A Multiple-meta-paths Simultaneous Learning Framework for Heterogeneous Information Network Embedding
• Temporal Network Embedding with Micro- and Macro-dynamics
• Meta-Path-Free Representation Learning on Heterogeneous Networks
• User-Guided Clustering in Heterogeneous Information Networks via Motif-Based Comprehensive Transcription